• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.187-194
• /
• 2015

In this paper, we present an effective visual odometry estimation system to track the real-time pose of a camera moving in 3D space. In order to meet the real-time requirement as well as to make full use of rich information from color and depth images, our system adopts a feature-based sparse odometry estimation method. After matching features extracted from across image frames, it repeats both the additional inlier set refinement and the motion refinement to get more accurate estimate of camera odometry. Moreover, even when the remaining inlier set is not sufficient, our system computes the final odometry estimate in proportion to the size of the inlier set, which improves the tracking success rate greatly. Through experiments with TUM benchmark datasets and implementation of the 3D scene reconstruction application, we confirmed the high performance of the proposed visual odometry estimation method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.89-92
• /
• 2005

Using natural speech commands for controlling a human-robot is an interesting topic in the field of robotics. In this paper, our main focus is on the verification of a speaker who gives a command to decide whether he/she is an authorized person for commanding. Among possible dynamic features of natural speech, pitch period is one of the most important ones for characterizing speech signals and it differs usually from person to person. However, current techniques of pitch detection are still not to a desired level of accuracy and robustness. When the signal is noisy or there are multiple pitch streams, the performance of most techniques degrades. In this paper, we propose a two-level approach for pitch detection which in compare with standard pitch detection algorithms, not only increases accuracy, but also makes the performance more robust to noise. In the first level of the proposed approach we discriminate voiced from unvoiced signals based on a neural classifier that utilizes cepstrum sequences of speech as an input feature set. Voiced signals are then further processed in the second level using a modified standard AMDF-based pitch detection algorithm to determine their pitch periods precisely. The experimental results show that the accuracy of the proposed system is better than those of conventional pitch detection algorithms for speech signals in clean and noisy environments.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.3
• /
• pp.453-459
• /
• 2008

The neural network is currently being used throughout numerous control system fields. However, it is not easy to obtain an input-output pattern when the neural network is used for the system of a single feedback controller and it is difficult to obtain satisfactory performance with when the load changes rapidly or disturbance is applied. To resolve these problems, this paper proposes a new mode to implement a neural network controller by installing a real object for control and an algorithm for this, which can replace the existing method of implementing a neural network controller by utilizing activation function at the output node. The real plant object for controlling of this mode implements a simple neural network controller replacing the activation function and provides the error back propagation path to calculate the error at the output node. As the controller is designed using a simple structure neural network, the input-output pattern problem is solved naturally and real-time learning becomes possible through the general error back propagation algorithm. The new algorithm applied neural network controller gives excellent performance for initial and tracking response and shows a robust performance for rapid load change and disturbance, in which the permissible error surpasses the range border. The effect of the proposed control algorithm was verified in a test that controlled the speed of a motor equipped with a high speed computing capable DSP on which the proposed algorithm was loaded.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.6
• /
• pp.10-21
• /
• 2000

The Cellular Noninear Networks structure for Distance Transform(DT) and the robust optical flow detection algorithm based on the DT are proposed. For some applications of optical flows such as target tracking and camera ego-motion computation, correct optical flows at a few feature points are more useful than unreliable one at every pixel point. The proposed algorithm is for detecting the optical flows on the trajectories only of the feature points. The translation lengths and the directions of feature movements are detected on the trajectories of feature points on which Distance Transform Field is developed. The robustness caused from the use of the Distance Transform and the easiness of hardware implementation with local analog circuits are the properties of the proposed structure. To verify the performance of the proposed structure and the algorithm, simulation has been done about various images under different noisy environment.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.6
• /
• pp.37-44
• /
• 1999

In this paper, we present a new sliding surface with a time-varying repeated root for fast and robust tracking of higher-order uncertain systems. The repeated root is moved to target one with stabilizing the closed-loop time-varying system in sliding mode. This initial root is obtained so that shifting distance of the surface may be minimized with respect to an initial error, and the intercept is produced so that the surface may pass the initial error. Under the allowable input, fast shifting of the surface and movement of the repeated root enable the error convergence rate to be increased. The proposed sliding mode control makes the error always remain on the surface from the beginning, and therefore, the system is more insensitive to parameter uncertainties and external disturbances. In simulation, the effectiveness of the proposed method is proved by comparison with the conventional one.

• The Journal of the Korea Contents Association
• /
• v.11 no.10
• /
• pp.1-10
• /
• 2011

In this paper, we proposed the skin color based hand and finger detection technology for the gesture recognition in CCTV surveillance. The aim of this paper is to present the methodology for hand detection and propose the finger detection method. The detected hand and finger can be used to implement the non-contact mouse. This technology can be used to control the home devices such as home-theater and television. Skin color is used to segment the hand region from background and contour is extracted from the segmented hand. Analysis of contour gives us the location of finger tip in the hand. After detecting the location of the fingertip, this system tracks the fingertip by using only R channel alone, and in recognition of hand motions to apply differential image, such as the removal of useless image shows a robust side. We explain about experiment which relates in fingertip tracking and finger gestures recognition, and experiment result shows the accuracy above 96%.

• Journal of Korea Multimedia Society
• /
• v.16 no.4
• /
• pp.483-492
• /
• 2013

SURF is an algorithm which extracts feature points and generates their descriptors from input images, and it is being used for many applications such as object recognition, tracking, and constructing panorama pictures. Although SURF is known to be robust to changes of scale, rotation, and view points, it is hard to implement it in real time due to its complex and repetitive computations. Using 3.3 GHz Pentium, in our experiment, it takes 240ms to extract feature points and create descriptors in a VGA image containing about 1,000 feature points, which means that software implementation cannot meet the real time requirement, especially in embedded systems. In this paper, we present a hardware architecture that can compute the SURF algorithm very fast while consuming minimum hardware resources. Two key concepts of our architecture are parallelism (for repetitive computations) and efficient line memory usage (obtained by analyzing memory access patterns). As a result of FPGA synthesis using Xilinx Virtex5LX330, it occupies 101,348 LUTs and 1,367 KB on-chip memory, giving performance of 30 frames per second at 100 MHz clock.

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1247-1259
• /
• 2005

This paper proposes a real-time face recognition system which detects multiple faces from low resolution video such as web-camera video. Face recognition system consists of the face detection step and the face classification step. At First, it finds face region candidates by using AdaBoost based object detection method which have fast speed and robust performance. It generates reduced feature vector for each face region candidate by using principle component analysis. At Second, Face classification used Principle Component Analysis and multi-SVM. Experimental result shows that the proposed method achieves real-time face detection and face recognition from low resolution video. Additionally, We implement the auto-tracking face recognition system using the Pan-Tilt Web-camera and radio On/Off digital door-lock system with face recognition system.

• International Journal of Aeronautical and Space Sciences
• /
• v.14 no.3
• /
• pp.247-255
• /
• 2013

The flight control of re-entry vehicles poses a challenge to conventional gain-scheduled flight controllers due to the widely spread aerodynamic coefficients. In addition, a wide range of uncertainties in disturbances must be accommodated by the control system. This paper presents the design of a roll channel controller for a non-axisymmetric reentry vehicle model using the trajectory linearization control (TLC) method. The dynamic equations of a moving mass system and roll control model are established using the Lagrange method. Nonlinear tracking and decoupling control by trajectory linearization can be viewed as the ideal gain-scheduling controller designed at every point along the flight trajectory. It provides robust stability and performance at all stages of the flight without adjusting controller gains. It is this "plug-and-play" feature that is highly preferred for developing, testing and routine operating of the re-entry vehicles. Although the controller is designed only for nominal aerodynamic coefficients, excellent performance is verified by simulation for wind disturbances and variations from -30% to +30% of the aerodynamic coefficients.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12C
• /
• pp.744-752
• /
• 2011

In intelligent surveillance system, various methods for detecting abnormal behavior were proposed recently. However, most researches are not robust enough to be utilized for actual reality which often has occlusions because of assumption the researches have that individual objects can be tracked. This paper presents a novel method to detect abnormal behavior by analysing major motion of the scene for complex environment in which object tracking cannot work. First, we generate Visual Word and Visual Document from motion information extracted from input video and process them through LDA(Latent Dirichlet Allocation) algorithm which is one of document analysis technique to obtain major motion information(location, magnitude, direction, distribution) of the scene. Using acquired information, we compare similarity between motion appeared in input video and analysed major motion in order to detect motions which does not match to major motions as abnormal behavior.